Please enable JavaScript.
Coggle requires JavaScript to display documents.
Language Model (How to create a language model (DATASET (https://archive…
Language Model
How to create a language model
https://www.analyticsvidhya.com/blog/2019/08/comprehensive-guide-language-model-nlp-python-code/
https://machinelearningmastery.com/how-to-develop-a-word-level-neural-language-model-in-keras/
https://machinelearningmastery.com/develop-word-based-neural-language-models-python-keras/
DATASET
https://archive.ics.uci.edu/ml/datasets/Devanagari+Handwritten+Character+Dataset#
https://towardsdatascience.com/learning-nlp-language-models-with-real-data-cdff04c51c25
if yes
first trying image caption
if no
create a new language model
Data collection
character recognition
Word recognition
https://blogs.nvidia.com/blog/2019/07/02/gpus-ai-ancient-sanskrit/
This one is related to character recognition, but no clues to github, or how he has trained, or architecture
https://sci-hub.se/10.1109/skima.2015.7400041
https://sci-hub.se/10.1109/acpr.2015.7486592
Image
collecting data's of scriptures
Google Image
Source Website
The holy bible in sanscript language
https://archive.org/details/holybibleinsansc00gill/mode/2up
https://archive.org/details/holybibleinsansc02weng/page/n4/mode/2up
souce website
palm leaf images in paintings about the scripture
http://odishamuseum.nic.in/?q=node/288
Keywords used for medicine: Atharvaveda
Sanskrit character recognition
sanskrit character recognition Deep learning
https://people.csail.mit.edu/yichangshih/mywebsite/sanskrit.pdf
IMAGES
WRITTEN
VEDAS
RIG VEDA
Samhitas
constitute the hymn part of the Vedas.
Brahmanas
These are commentaries on the Vedic mantras. They are written in prose and deal mainly with rituals connected with sacrifices.
Aranyakas
Are the concluding parts of the Brahmanas. Aranyakas mean 'forest books'. They do not deal with rituals but are concerned with mysticism and philosophy. They lay more stress on knowledge of God, soul, world and man.
https://www.sacred-texts.com/hin/rvsan/index.htm
YAJUR VEDA
SAMA VEDA
ATHARVA VEDA
MEDICAL PURPOSE
LINKS
https://www.quora.com/Where-are-the-original-vedas-kept
https://lrc.la.utexas.edu/eieol/vedol/10
stone manuscript
palm leaves manuscript
wall manuscripts
Painting
LINKS
https://sanskritdocuments.org/
https://archive.org/search.php?query=SANSKRIT
https://sanskritdocuments.org/scannedbooks/
keywords
sandhi-meaning "connection"
palaeography
the study of ancient writing systems and the deciphering and dating of historical manuscripts.
http://gretil.sub.uni-goettingen.de/gretil.html
https://diuf.unifr.ch/main/hisdoc/hisdoc-iii
https://diuf.unifr.ch/main/hisdoc/hisdoc-iii-represented-das-2018-vienna
https://diuf.unifr.ch/main/hisdoc/divaservices
https://diva-dia.github.io/DeepDIVAweb/
http://www.parankusa.org/Main.aspx
PROCESSING
DECIPHER
https://blogs.nvidia.com/blog/2019/07/02/gpus-ai-ancient-sanskrit/
oliver hellwig statistical model
https://uzh.academia.edu/OliverHellwig
word segmentation
https://www.academia.edu/37706328/Sanskrit_Word_Segmentation_Using_Character-level_Recurrent_and_Convolutional_Neural_Networks
https://www.researchgate.net/profile/Oliver_Hellwig
https://dblp.org/pers/h/Hellwig:Oliver.html
https://www.aclweb.org/anthology/D18-1295/
https://github.com/OliverHellwig
https://www.semanticscholar.org/paper/Extracting-Dependency-Trees-from-Sanskrit-Texts-Hellwig/fe876f043970d2f06b04667fdcd473a439098d9f
https://www.aclweb.org/anthology/W19-7505.pdf
https://github.com/tylergneill/pramana-nlp
Need to see the entire git repos given by this person
http://sanskrit.uohyd.ac.in/Corpus/
Topic Modeling and Latent Dirichlet Allocation (LDA)
pramāṇa texts
https://sci-hub.se/https://link.springer.com/chapter/10.1007/978-3-642-17528-2_12
CORPUS Manager
https://pdfs.semanticscholar.org/0199/362512872bf87268cda7d66f9e899ac2cac2.pdf
https://gitlab.inria.fr/huet/Heritage_Resources
Word Segmentation and Morphological Tagging
https://arxiv.org/pdf/1809.01446.pdf
https://bsantraigi.github.io/papers/coling16a.pdf
https://hal.inria.fr/inria-00203467/file/Hellwig.pdf
https://www.quora.com/Does-Zipfs-law-apply-to-Sanskrit
Zipf's law
tree bank of vedic sanskrit oliver hellwig
https://www.aclweb.org/anthology/W19-75.pdf
https://github.com/Jivnesh/ISCLS-19
1 more item...
https://github.com/sebastian-nehrdich/gretil-quotations
1 more item...
Transliteration
2 more items...
https://technoidhub.com/machine-learning/ai-helps-researcher-decode-ancient-sanskrit-using-nvidia-quadro-gpu/17174/
https://medium.com/@nickmalhotra/towards-an-improved-man-and-machine-connect-using-sanskrit-dd6878e20655
TESSERACT
https://nanonets.com/blog/tag/optical-character-recognition/
https://github.com/tesseract-ocr/tessdoc
https://github.com/tesseract-ocr/tessdoc/blob/master/Training-Tesseract.md
https://github.com/tesseract-ocr/tessdoc/blob/master/TrainingTesseract-4.00.md#training-text-requirements
https://sourceforge.net/p/tesseracthindi/wiki/OCR%20for%20Devanagari/
https://github.com/tesseract-ocr/tessdata/issues/61
EPIGRAPHY
https://github.com/sommerschield/ancient-text-restoration
Restoring ancient text using deep learning
https://deepmind.com/research/publications/Restoring-ancient-text-using-deep-learning-a-case-study-on-Greek-epigraphy
TRANSLATION
DATASET
http://sanskrit.safire.com/Sanskrit.html#stotras
http://lca.wisc.edu/~gbuhnema/texts.html
https://drive.google.com/drive/u/0/folders/0B37fn75wcwOsbUNpeFQzOUx3a2c
http://www.sanskritweb.net/rigveda/
http://www.sanskritweb.net/rigveda/griffith.pdf
ATHARVA-VEDA
https://www.sacred-texts.com/hin/av/av01003.htm
TRANSLITERATION
http://titus.uni-frankfurt.de/texte/etcs/ind/aind/ved/av/avs/avs.htm
SANSKRIT
https://www.shastras.com/vedas/atharva-veda/
UNICODE
https://unicode.org/L2/L2015/15101-vedic.pdf
AUDIO
VEDAS AUDIO RECORDS
http://www.svvedicuniversity.ac.in/svvrp/svvrp.php
Data Source
egangotri
https://archive.org/search.php?query=atharva%20manuscripts
https://archive.org/details/MN003295AtharvaVediGarudaUpanishadDevanagariSanskritManuscriptsAtKurukshetraUniversity/page/n1/mode/2up
https://archive.org/details/AtharvaVedaSamhita5280Alm24Shlf1DevanagariVed/page/n19/mode/2up
sanskrit manuscript language
https://indology.info/links/img/
https://archive.org/details/@upss_manuscripts?&sort=-publicdate&page=2
https://archive.org/details/4149UPSSSharadaRagyiSahasranaamPg1To18Complete/page/n9/mode/2up
https://cudl.lib.cam.ac.uk/collections/sanskrit/1
sanskrit character recognition Deep learning
https://people.csail.mit.edu/yichangshih/mywebsite/sanskrit.pdf
ETL character database
http://etlcdb.db.aist.go.jp/
http://etlcdb.db.aist.go.jp/obtaining-etl-character-database
Character Recognition
Japanese character Recognition
https://github.com/charlietsai/japanese-handwriting-nn
https://colab.research.google.com/github/charlietsai/japanese-handwriting-nn/blob/master/visualization.ipynb
Devanagiri Character Recognition
https://towardsdatascience.com/devanagari-script-character-recognition-using-machine-learning-6006b40fa6a9
https://www.kaggle.com/rishianand/devanagari-character-set
https://github.com/rishianand54/devanagari-character-recognition-system/blob/master/DCRS.ipynb
Sanskrit Language model
Audio
VACHASPATHYAM
data collection pipeline
Image Preprocessing
Optical Character Recognition
Digitized Text
Shabda Kalpadruma
KEYWORDS
GIT
QUORA
LINKS
Need to look into it
git inside this